Blog / Explainer
Explainer

What is MCP — and how does it let AI share real links?

Model Context Protocol is the open standard that lets AI assistants use external tools. Here's what that means in plain terms, how remote MCP servers differ from local ones, and how it makes sharing AI-built work as simple as saying "share this."

If you've used an AI assistant to build something — a dashboard, a landing page, a quick internal tool — you've probably hit the same wall: the thing exists inside the AI session, and getting it in front of someone else is awkward. MCP is the reason that's changing.

Model Context Protocol, explained simply

MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external tools and services. Think of it as USB for AI: a single, standardized plug that works across clients and tools, so nobody has to build custom integrations for every combination.

Before MCP, if you wanted an AI assistant to do something beyond text — check a database, send an email, deploy a page — someone had to build a bespoke integration between that specific AI and that specific service. MCP replaces that with a common protocol. Any AI client that speaks MCP can use any tool that speaks MCP.

The protocol was introduced by Anthropic and has since been adopted across the industry. It defines how an AI client discovers what tools a server offers, how it calls them, and how results come back — all over a standard transport (HTTP with server-sent events, or stdio for local tools).

Remote MCP servers vs. local ones

MCP servers come in two flavors, and the difference matters:

Sharing is a good example of something that requires a remote server. To give someone a link they can open in a browser, the content needs to be hosted somewhere public. A local MCP server can't do that — a remote one can.

How Bauta uses MCP to share what AI builds

Bauta is a remote MCP server. Connect it to any MCP-compatible AI client, and that client gains the ability to deploy HTML and React to live, shareable URLs. The AI doesn't just generate code — it publishes it to a real page that anyone can open in a browser.

The workflow is four steps, and only one of them is yours:

  1. Connect. Add Bauta's MCP endpoint (https://bauta.app/mcp) to your AI client. Authorize in the browser. This takes about a minute and you only do it once.
  2. Build. Ask your AI to build whatever you need — a dashboard, a report, a landing page, a tool.
  3. Share. Say "share this" (or "deploy this," or "publish this"). The AI calls Bauta's deploy_artifact tool and publishes the work to a live URL.
  4. Send the link. That's it. The recipient opens it in any browser. No installs, no accounts, no dev tools.
Private by default. Every link starts as unlisted — only people with the exact URL can see it. You can change sharing to public, password-protected, email-gated, or fully private at any time. Full security details.

Which AI clients support MCP

MCP adoption has grown quickly. Here are the clients you can use with Bauta today:

ClientTypeSetup
Claude (web & desktop)Remote MCP connectorAdd as connector
Claude CodeCLI agentOne terminal command
ChatGPTRemote MCP connectorAdd as connector
CodexCloud agentMCP config
CursorCode editorSettings UI or mcp.json
WindsurfCode editorSame MCP config as Cursor
CoworkTeam AI workspacePlugin

Same Bauta account, same URLs, same sharing controls — regardless of which client you use. Build in Claude, update from Cursor, adjust sharing from ChatGPT. The sharing layer doesn't care where the request came from.

Step by step: how MCP sharing works

Here's the concrete version. We'll use Claude as the example, but the flow is identical in any MCP-compatible client.

1. Connect Bauta

In your AI client, add Bauta as an MCP server. The URL is always the same:

https://bauta.app/mcp

When you connect for the first time, your client opens a browser window for authentication. Sign in or create an account — it's the same step. Authorization uses OAuth, so no API keys to copy around.

2. Ask the AI to build something

Ask for whatever you need. A client report. An interactive prototype. A comparison table. A landing page draft. The AI builds it as it always would.

3. Say "share this"

One sentence is enough. The AI calls Bauta's deploy tool, uploads the HTML (compiling JSX if needed), and returns a live URL:

Published to https://share.bauta.app/k9m2p Unlisted — only people with this link can see it.

4. Send the link

That URL works in any browser, on any device. The recipient doesn't need your AI client, doesn't need developer tools, doesn't need an account. If you update the content and republish, the same URL updates in place. Previous versions stay in version history.

Frequently asked questions

What is the Model Context Protocol?
MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external tools and services. It defines how clients discover tools, call them, and receive results — over HTTP for remote servers or stdio for local ones. Think of it as a universal plug: any AI client that speaks MCP can use any MCP server, without custom integrations.
Which AI clients support MCP?
Claude (web, desktop, and Code), ChatGPT, Codex, Cursor, Windsurf, and Cowork all support MCP today. Any of them can connect to Bauta — same account, same URLs, same sharing controls. The list continues to grow as more clients adopt the standard.
Do I need to install anything?
No. Bauta is a remote MCP server. Your AI client connects to a URL (https://bauta.app/mcp) over the internet. There's nothing to download, no packages to install, and no local server to run. You add the URL, authorize in the browser, and you're connected.
Is my shared content public?
Not by default. Everything you deploy through Bauta starts as unlisted — only people with the exact secret link can open it. You can change sharing to public, password-protected, email-gated (paid plans), or fully private at any time. Content is served from an isolated sandbox domain and hosted in the EU. Full security details.

Try MCP sharing in two minutes

Connect Bauta to your AI client, build something, and say "share this." Free plan, no credit card, works with any MCP-compatible client.

Set up Bauta